Files
Evection/apps/core/views.py
T
ksmithandClaude Sonnet 5.5 fd494a9c08 Make the readiness check catch fetching that is scheduled but failing (#27)
/health/ready/ proved beat and a worker were alive but not that
fetching worked: every feed could be failing, or the queue could be
hours behind, and it would still report ok.

apps.core.health adds three checks: Celery queue depth (real Redis list
length, over 1000 fails), a successful fetch within three poll intervals
(30 min minimum, with a grace period for a brand-new install), and the
share of active feeds failing (over half, once there are at least four).
The payload also reports queue depth, active/failing feed counts, and
the age of the last successful fetch. Verified against real Redis with
queued Celery tasks, and the suite on PostgreSQL. docs/install.md lists
each check.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-01 09:30:00 -07:00

115 lines
4.1 KiB
Python

from django.contrib import messages
from django.contrib.auth.decorators import user_passes_test
from django.core.cache import cache
from django.db import connection
from django.db.models import Count, Min, Q
from django.http import JsonResponse
from django.shortcuts import get_object_or_404, redirect, render
from django.utils import timezone
from django.views.decorators.http import require_POST
from apps.articles.models import Article
from apps.feeds.models import Feed, Subscription
from apps.feeds.tasks import POLL_HEARTBEAT_CACHE_KEY, fetch_feed, reset_feed_backoff
from .health import fetch_pipeline_status
is_admin = user_passes_test(lambda u: u.is_authenticated and u.is_staff)
# Beat ticks poll_due_feeds every minute; this many minutes without a tick
# means beat or the worker (or the broker between them) isn't working.
POLL_HEARTBEAT_MAX_AGE_SECONDS = 5 * 60
def health(request):
"""Unauthenticated liveness check — reachable even before
first-run setup (see SetupWizardMiddleware). Used by scripts/upgrade.sh
to confirm a freshly restarted deploy actually came up, and is a
reasonable target for any external uptime monitor too."""
try:
with connection.cursor() as cursor:
cursor.execute("SELECT 1")
except Exception:
return JsonResponse({"status": "error"}, status=503)
return JsonResponse({"status": "ok"})
def health_ready(request):
"""Readiness: liveness plus everything background fetching depends on
(C8) — the database, the Redis cache/broker, and a recent
poll_due_feeds tick, which proves beat is scheduling AND a worker is
consuming. Beyond that tick, apps.core.health checks fetching is
actually succeeding: queue depth, a recent successful fetch, and the
share of feeds failing. /health/ above stays DB-only on purpose: scripts/upgrade.sh
gates a deploy on it right after restart, before beat has had a
chance to tick. Point an uptime monitor at this one instead."""
checks = {"database": False, "redis": False, "poll_heartbeat": False}
detail = {}
try:
with connection.cursor() as cursor:
cursor.execute("SELECT 1")
checks["database"] = True
except Exception:
pass
try:
cache.set("health-ready-probe", "1", timeout=10)
checks["redis"] = cache.get("health-ready-probe") == "1"
except Exception:
pass
try:
last_tick = cache.get(POLL_HEARTBEAT_CACHE_KEY)
except Exception:
last_tick = None
if last_tick is not None:
age = (timezone.now() - last_tick).total_seconds()
detail["poll_heartbeat_age_seconds"] = int(age)
checks["poll_heartbeat"] = age <= POLL_HEARTBEAT_MAX_AGE_SECONDS
if checks["database"]:
pipeline_checks, pipeline_detail = fetch_pipeline_status()
checks.update(pipeline_checks)
detail.update(pipeline_detail)
ok = all(checks.values())
return JsonResponse(
{"status": "ok" if ok else "degraded", "checks": checks, **detail},
status=200 if ok else 503,
)
@is_admin
def dashboard(request):
feeds = Feed.objects.annotate(subscriber_count=Count("subscriptions"))
erroring_feeds = feeds.filter(
Q(last_fetch_status=Feed.STATUS_ERROR) | Q(fetch_error_count__gt=0)
).order_by("-fetch_error_count")
stats = {
"feed_count": feeds.count(),
"active_feed_count": feeds.filter(is_active=True).count(),
"error_feed_count": erroring_feeds.count(),
"subscription_count": Subscription.objects.count(),
"article_count": Article.objects.count(),
"oldest_article_at": Article.objects.aggregate(oldest=Min("fetched_at"))["oldest"],
}
return render(
request,
"core/dashboard.html",
{"stats": stats, "erroring_feeds": erroring_feeds},
)
@is_admin
@require_POST
def retry_feed(request, feed_id):
feed = get_object_or_404(Feed, pk=feed_id)
reset_feed_backoff.delay(feed.id)
fetch_feed.delay(feed.id)
messages.success(request, f"Queued an immediate retry for '{feed.title or feed.feed_url}'.")
return redirect("core:dashboard")